Analysis and Best Parameters Selection for Person Recognition based on Gait model using CNN algorithm and Image Augmentation
Abstract Person recognition based on gait model and motion print is indeed a challenging and novel task due to its usages and to the critical issues of human pose variation, human body occlusion, camera view variation, etc. In this project, a deep convolution neural network (CNN) was modified and adapted for person recognition with image augmentation technique. CNN is best algorithm of deep learning algorithms. Adaptation aims to get best values for CNN parameters to get best CNN model. In Addition to the CNN parameters, the design of CNN model itself was adapted to get best model design; number of layers and normalization between them. After choosing best parameters and best design, Image augmentation was used to increase train dataset with many copies of the image to boost the number of different images that will be used to train Deep learning algorithms. The tests were achieved using known dataset (Market dataset). The dataset contains sequential pictures of people in different gait status. The image in CNN model as matrix is extracted to many images or matrices, so dataset size may be bigger by hundred times to make the problem a big data problem, in this project Results show that adaptation has improved the accuracy of person recognition using gait model, that is represented in many successive images for the same person. In addition, dataset contains images of person carrying things. The improved model of CNN is robust to image dimensions (quality and resolution) and to carried things by persons.